Dolly v2 Models

**Overview**

The Dolly_v2 models are large language models (LLMs) developed by Databricks. The models provided in this listing are

- [dolly_v2_12b](https://huggingface.co/databricks/dolly-v2-12b)
- [dolly_v2_3b](https://huggingface.co/databricks/dolly-v2-3b)
- [dolly_v2_7b](https://huggingface.co/databricks/dolly-v2-7b)

The models are packaged using MLflow’s transformers flavor.
- [dolly_v2_12b](https://huggingface.co/databricks/dolly-v2-12b), [dolly_v2_3b](https://huggingface.co/databricks/dolly-v2-3b), [dolly_v2_7b](https://huggingface.co/databricks/dolly-v2-7b): instruct fine-tuned for short-form instruction following.

Dolly_v2 models are licensed under the [MIT License](https://choosealicense.com/licenses/mit/). By installing this listing, you acknowledge and agree to the license.

For example notebooks of using the dolly_v2 model in various use cases on Databricks, refer to [the Databricks ML example repository](https://github.com/databricks/databricks-ml-examples/tree/master/llm-models/dolly_v2).

**Use cases**

[dolly_v2_12b](https://huggingface.co/databricks/dolly-v2-12b), [dolly_v2_3b](https://huggingface.co/databricks/dolly-v2-3b), [dolly_v2_7b](https://huggingface.co/databricks/dolly-v2-7b):
- Generating responses to text-based instructions

**Product details**

The pre-trained model can be used for further fine-tuning on specific applications. The fine-tuned model in this listing can be deployed directly to Databricks Model Serving for immediate use, or loaded for fine-tuning or batch inference use cases. For more details, install the listing and view the provided model cards for each model.

搜集汇总

背景与挑战

背景概述

Dolly v2 Models是由Databricks开发的大型语言模型，包含12B、3B和7B三个参数规模的版本，这些模型经过指令微调，适用于生成文本指令响应，并采用MLflow的transformer格式打包，遵循MIT许可证许可。